
TRP: Trained Rank Pruning for Efficient Deep Neural Networks
To enable DNNs on edge devices like mobile phones, lowrank approximatio...
read it

Learning Lowrank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification
Modern deep neural networks (DNNs) often require high memory consumption...
read it

Neural Predictor for Neural Architecture Search
Neural Architecture Search methods are effective but often use complex a...
read it

Traned Rank Pruning for Efficient Deep Neural Networks
To accelerate DNNs inference, lowrank approximation has been widely ado...
read it

Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30
Generative adversarial network (GAN) has greatly improved the quality of...
read it

DeepHoyer: Learning Sparser Neural Network with Differentiable ScaleInvariant Sparsity Measures
In seeking for sparse and efficient neural network models, many previous...
read it

Joint Pruning on Activations and Weights for Efficient Neural Networks
With rapidly scaling up of deep neural networks (DNNs), extensive resear...
read it

AutoGrow: Automatic Layer Growing in Deep Convolutional Networks
We propose AutoGrow to automate depth discovery in Deep Neural Networks ...
read it

PruneTrain: Gradual Structured Pruning from Scratch for Faster Neural Network Training
Model pruning is a popular mechanism to make a network more efficient fo...
read it

Trained Rank Pruning for Efficient Deep Neural Networks
The performance of Deep Neural Networks (DNNs) keeps elevating in recent...
read it

Minibatch Serialization: CNN Training with Interlayer Data Reuse
Training convolutional neural networks (CNNs) requires intense computati...
read it

SmoothOut: Smoothing Out Sharp Minima for Generalization in LargeBatch Deep Learning
In distributed deep learning, a large batch size in Stochastic Gradient ...
read it

ConPredictor: Concurrency Defect Prediction in RealWorld Applications
Concurrent programs are difficult to test due to their inherent nondete...
read it

Learning Intrinsic Sparse Structures within Long ShortTerm Memory
Model compression is significant for the wide adoption of Recurrent Neur...
read it

TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
High network communication cost for synchronizing gradients and paramete...
read it

Coordinating Filters for Faster Deep Neural Networks
Very largescale Deep Neural Networks (DNNs) have achieved remarkable su...
read it

A Compact DNN: Approaching GoogLeNetLevel Accuracy of Classification and Domain Adaptation
Recently, DNN model compression based on network architecture design, e....
read it

Group Scissor: Scaling Neuromorphic Computing Design to Large Neural Networks
Synapse crossbar is an elementary structure in Neuromorphic Computing Sy...
read it

Classification Accuracy Improvement for Neuromorphic Computing Systems with Onelevel Precision Synapses
Brain inspired neuromorphic computing has demonstrated remarkable advant...
read it

Learning Structured Sparsity in Deep Neural Networks
High demand for computation resources severely hinders deployment of lar...
read it

Faster CNNs with Direct Sparse Convolutions and Guided Pruning
Phenomenally successful in practical inference problems, convolutional n...
read it

A New Learning Method for Inference Accuracy, Core Occupation, and Performance Cooptimization on TrueNorth Chip
IBM TrueNorth chip uses digital spikes to perform neuromorphic computing...
read it